8 files changed, 121 insertions, 67 deletions

diff --git a/kernel/sched/core.c b/kernel/sched/core.c
index 268a45ea238c..0a7251678982 100644
--- a/kernel/sched/core.c
+++ b/kernel/sched/core.c
@@ -2192,7 +2192,7 @@ static inline void post_schedule(struct rq *rq)
  * schedule_tail - first thing a freshly forked thread must call.
  * @prev: the thread we just switched away from.
  */
-asmlinkage void schedule_tail(struct task_struct *prev)
+asmlinkage __visible void schedule_tail(struct task_struct *prev)
         __releases(rq->lock)
 {
         struct rq *rq = this_rq();
@@ -2592,8 +2592,14 @@ pick_next_task(struct rq *rq, struct task_struct *prev)
         if (likely(prev->sched_class == class &&
                    rq->nr_running == rq->cfs.h_nr_running)) {
                 p = fair_sched_class.pick_next_task(rq, prev);
-                if (likely(p && p != RETRY_TASK))
-                        return p;
+                if (unlikely(p == RETRY_TASK))
+                        goto again;
+
+                /* assumes fair_sched_class->next == idle_sched_class */
+                if (unlikely(!p))
+                        p = idle_sched_class.pick_next_task(rq, prev);
+
+                return p;
         }
 
 again:
@@ -2741,7 +2747,7 @@ static inline void sched_submit_work(struct task_struct *tsk)
                 blk_schedule_flush_plug(tsk);
 }
 
-asmlinkage void __sched schedule(void)
+asmlinkage __visible void __sched schedule(void)
 {
         struct task_struct *tsk = current;
 
@@ -2751,7 +2757,7 @@ asmlinkage void __sched schedule(void)
 EXPORT_SYMBOL(schedule);
 
 #ifdef CONFIG_CONTEXT_TRACKING
-asmlinkage void __sched schedule_user(void)
+asmlinkage __visible void __sched schedule_user(void)
 {
         /*
          * If we come here after a random call to set_need_resched(),
@@ -2783,7 +2789,7 @@ void __sched schedule_preempt_disabled(void)
  * off of preempt_enable. Kernel preemptions off return from interrupt
  * occur there and call schedule directly.
  */
-asmlinkage void __sched notrace preempt_schedule(void)
+asmlinkage __visible void __sched notrace preempt_schedule(void)
 {
         /*
          * If there is a non-zero preempt_count or interrupts are disabled,
@@ -2813,7 +2819,7 @@ EXPORT_SYMBOL(preempt_schedule);
  * Note, that this is called and return with irqs disabled. This will
  * protect us against recursive calling from irq.
  */
-asmlinkage void __sched preempt_schedule_irq(void)
+asmlinkage __visible void __sched preempt_schedule_irq(void)
 {
         enum ctx_state prev_state;
 
@@ -3124,6 +3130,7 @@ __setparam_dl(struct task_struct *p, const struct sched_attr *attr)
         dl_se->dl_bw = to_ratio(dl_se->dl_period, dl_se->dl_runtime);
         dl_se->dl_throttled = 0;
         dl_se->dl_new = 1;
+        dl_se->dl_yielded = 0;
 }
 
 static void __setscheduler_params(struct task_struct *p,
@@ -3188,17 +3195,40 @@ __getparam_dl(struct task_struct *p, struct sched_attr *attr)
  * We ask for the deadline not being zero, and greater or equal
  * than the runtime, as well as the period of being zero or
  * greater than deadline. Furthermore, we have to be sure that
- * user parameters are above the internal resolution (1us); we
- * check sched_runtime only since it is always the smaller one.
+ * user parameters are above the internal resolution of 1us (we
+ * check sched_runtime only since it is always the smaller one) and
+ * below 2^63 ns (we have to check both sched_deadline and
+ * sched_period, as the latter can be zero).
  */
 static bool
 __checkparam_dl(const struct sched_attr *attr)
 {
-        return attr && attr->sched_deadline != 0 &&
-                (attr->sched_period == 0 ||
-                (s64)(attr->sched_period   - attr->sched_deadline) >= 0) &&
-                (s64)(attr->sched_deadline - attr->sched_runtime ) >= 0  &&
-                attr->sched_runtime >= (2 << (DL_SCALE - 1));
+        /* deadline != 0 */
+        if (attr->sched_deadline == 0)
+                return false;
+
+        /*
+         * Since we truncate DL_SCALE bits, make sure we're at least
+         * that big.
+         */
+        if (attr->sched_runtime < (1ULL << DL_SCALE))
+                return false;
+
+        /*
+         * Since we use the MSB for wrap-around and sign issues, make
+         * sure it's not set (mind that period can be equal to zero).
+         */
+        if (attr->sched_deadline & (1ULL << 63) ||
+            attr->sched_period & (1ULL << 63))
+                return false;
+
+        /* runtime <= deadline <= period (if period != 0) */
+        if ((attr->sched_period != 0 &&
+             attr->sched_period < attr->sched_deadline) ||
+            attr->sched_deadline < attr->sched_runtime)
+                return false;
+
+        return true;
 }
 
 /*
@@ -3639,6 +3669,7 @@ SYSCALL_DEFINE2(sched_setparam, pid_t, pid, struct sched_param __user *, param)
  * sys_sched_setattr - same as above, but with extended sched_attr
  * @pid: the pid in question.
  * @uattr: structure containing the extended parameters.
+ * @flags: for future extension.
  */
 SYSCALL_DEFINE3(sched_setattr, pid_t, pid, struct sched_attr __user *, uattr,
                                unsigned int, flags)
@@ -3650,8 +3681,12 @@ SYSCALL_DEFINE3(sched_setattr, pid_t, pid, struct sched_attr __user *, uattr,
         if (!uattr || pid < 0 || flags)
                 return -EINVAL;
 
-        if (sched_copy_attr(uattr, &attr))
-                return -EFAULT;
+        retval = sched_copy_attr(uattr, &attr);
+        if (retval)
+                return retval;
+
+        if (attr.sched_policy < 0)
+                return -EINVAL;
 
         rcu_read_lock();
         retval = -ESRCH;
@@ -3701,7 +3736,7 @@ SYSCALL_DEFINE1(sched_getscheduler, pid_t, pid)
  */
 SYSCALL_DEFINE2(sched_getparam, pid_t, pid, struct sched_param __user *, param)
 {
-        struct sched_param lp;
+        struct sched_param lp = { .sched_priority = 0 };
         struct task_struct *p;
         int retval;
 
@@ -3718,11 +3753,8 @@ SYSCALL_DEFINE2(sched_getparam, pid_t, pid, struct sched_param __user *, param)
         if (retval)
                 goto out_unlock;
 
-        if (task_has_dl_policy(p)) {
-                retval = -EINVAL;
-                goto out_unlock;
-        }
-        lp.sched_priority = p->rt_priority;
+        if (task_has_rt_policy(p))
+                lp.sched_priority = p->rt_priority;
         rcu_read_unlock();
 
         /*
@@ -3783,6 +3815,7 @@ err_size:
  * @pid: the pid in question.
  * @uattr: structure containing the extended parameters.
  * @size: sizeof(attr) for fwd/bwd comp.
+ * @flags: for future extension.
  */
 SYSCALL_DEFINE4(sched_getattr, pid_t, pid, struct sched_attr __user *, uattr,
                 unsigned int, size, unsigned int, flags)
@@ -5043,7 +5076,6 @@ static int sched_cpu_active(struct notifier_block *nfb,
                                       unsigned long action, void *hcpu)
 {
         switch (action & ~CPU_TASKS_FROZEN) {
-        case CPU_STARTING:
         case CPU_DOWN_FAILED:
                 set_cpu_active((long)hcpu, true);
                 return NOTIFY_OK;
@@ -6017,6 +6049,8 @@ sd_numa_init(struct sched_domain_topology_level *tl, int cpu)
                                         ,
                 .last_balance           = jiffies,
                 .balance_interval       = sd_weight,
+                .max_newidle_lb_cost    = 0,
+                .next_decay_max_lb_cost = jiffies,
         };
         SD_INIT_NAME(sd, NUMA);
         sd->private = &tl->data;
diff --git a/kernel/sched/cpudeadline.c b/kernel/sched/cpudeadline.c
index 5b9bb42b2d47..bd95963dae80 100644
--- a/kernel/sched/cpudeadline.c
+++ b/kernel/sched/cpudeadline.c
@@ -13,6 +13,7 @@
 
 #include <linux/gfp.h>
 #include <linux/kernel.h>
+#include <linux/slab.h>
 #include "cpudeadline.h"
 
 static inline int parent(int i)
@@ -39,8 +40,10 @@ static void cpudl_exchange(struct cpudl *cp, int a, int b)
 {
         int cpu_a = cp->elements[a].cpu, cpu_b = cp->elements[b].cpu;
 
-        swap(cp->elements[a], cp->elements[b]);
-        swap(cp->cpu_to_idx[cpu_a], cp->cpu_to_idx[cpu_b]);
+        swap(cp->elements[a].cpu, cp->elements[b].cpu);
+        swap(cp->elements[a].dl , cp->elements[b].dl );
+
+        swap(cp->elements[cpu_a].idx, cp->elements[cpu_b].idx);
 }
 
 static void cpudl_heapify(struct cpudl *cp, int idx)
@@ -140,7 +143,7 @@ void cpudl_set(struct cpudl *cp, int cpu, u64 dl, int is_valid)
         WARN_ON(!cpu_present(cpu));
 
         raw_spin_lock_irqsave(&cp->lock, flags);
-        old_idx = cp->cpu_to_idx[cpu];
+        old_idx = cp->elements[cpu].idx;
         if (!is_valid) {
                 /* remove item */
                 if (old_idx == IDX_INVALID) {
@@ -155,8 +158,8 @@ void cpudl_set(struct cpudl *cp, int cpu, u64 dl, int is_valid)
                 cp->elements[old_idx].dl = cp->elements[cp->size - 1].dl;
                 cp->elements[old_idx].cpu = new_cpu;
                 cp->size--;
-                cp->cpu_to_idx[new_cpu] = old_idx;
-                cp->cpu_to_idx[cpu] = IDX_INVALID;
+                cp->elements[new_cpu].idx = old_idx;
+                cp->elements[cpu].idx = IDX_INVALID;
                 while (old_idx > 0 && dl_time_before(
                                 cp->elements[parent(old_idx)].dl,
                                 cp->elements[old_idx].dl)) {
@@ -173,7 +176,7 @@ void cpudl_set(struct cpudl *cp, int cpu, u64 dl, int is_valid)
                 cp->size++;
                 cp->elements[cp->size - 1].dl = 0;
                 cp->elements[cp->size - 1].cpu = cpu;
-                cp->cpu_to_idx[cpu] = cp->size - 1;
+                cp->elements[cpu].idx = cp->size - 1;
                 cpudl_change_key(cp, cp->size - 1, dl);
                 cpumask_clear_cpu(cpu, cp->free_cpus);
         } else {
@@ -195,10 +198,21 @@ int cpudl_init(struct cpudl *cp)
         memset(cp, 0, sizeof(*cp));
         raw_spin_lock_init(&cp->lock);
         cp->size = 0;
-        for (i = 0; i < NR_CPUS; i++)
-                cp->cpu_to_idx[i] = IDX_INVALID;
-        if (!alloc_cpumask_var(&cp->free_cpus, GFP_KERNEL))
+
+        cp->elements = kcalloc(nr_cpu_ids,
+                               sizeof(struct cpudl_item),
+                               GFP_KERNEL);
+        if (!cp->elements)
+                return -ENOMEM;
+
+        if (!alloc_cpumask_var(&cp->free_cpus, GFP_KERNEL)) {
+                kfree(cp->elements);
                 return -ENOMEM;
+        }
+
+        for_each_possible_cpu(i)
+                cp->elements[i].idx = IDX_INVALID;
+
         cpumask_setall(cp->free_cpus);
 
         return 0;
@@ -210,7 +224,6 @@ int cpudl_init(struct cpudl *cp)
  */
 void cpudl_cleanup(struct cpudl *cp)
 {
-        /*
-         * nothing to do for the moment
-         */
+        free_cpumask_var(cp->free_cpus);
+        kfree(cp->elements);
 }
diff --git a/kernel/sched/cpudeadline.h b/kernel/sched/cpudeadline.h
index a202789a412c..538c9796ad4a 100644
--- a/kernel/sched/cpudeadline.h
+++ b/kernel/sched/cpudeadline.h
@@ -5,17 +5,17 @@
 
 #define IDX_INVALID     -1
 
-struct array_item {
+struct cpudl_item {
         u64 dl;
         int cpu;
+        int idx;
 };
 
 struct cpudl {
         raw_spinlock_t lock;
         int size;
-        int cpu_to_idx[NR_CPUS];
-        struct array_item elements[NR_CPUS];
         cpumask_var_t free_cpus;
+        struct cpudl_item *elements;
 };
 
 
diff --git a/kernel/sched/cpupri.c b/kernel/sched/cpupri.c
index 8b836b376d91..8834243abee2 100644
--- a/kernel/sched/cpupri.c
+++ b/kernel/sched/cpupri.c
@@ -30,6 +30,7 @@
 #include <linux/gfp.h>
 #include <linux/sched.h>
 #include <linux/sched/rt.h>
+#include <linux/slab.h>
 #include "cpupri.h"
 
 /* Convert between a 140 based task->prio, and our 102 based cpupri */
@@ -70,8 +71,7 @@ int cpupri_find(struct cpupri *cp, struct task_struct *p,
         int idx = 0;
         int task_pri = convert_prio(p->prio);
 
-        if (task_pri >= MAX_RT_PRIO)
-                return 0;
+        BUG_ON(task_pri >= CPUPRI_NR_PRIORITIES);
 
         for (idx = 0; idx < task_pri; idx++) {
                 struct cpupri_vec *vec  = &cp->pri_to_cpu[idx];
@@ -219,8 +219,13 @@ int cpupri_init(struct cpupri *cp)
                         goto cleanup;
         }
 
+        cp->cpu_to_pri = kcalloc(nr_cpu_ids, sizeof(int), GFP_KERNEL);
+        if (!cp->cpu_to_pri)
+                goto cleanup;
+
         for_each_possible_cpu(i)
                 cp->cpu_to_pri[i] = CPUPRI_INVALID;
+
         return 0;
 
 cleanup:
@@ -237,6 +242,7 @@ void cpupri_cleanup(struct cpupri *cp)
 {
         int i;
 
+        kfree(cp->cpu_to_pri);
         for (i = 0; i < CPUPRI_NR_PRIORITIES; i++)
                 free_cpumask_var(cp->pri_to_cpu[i].mask);
 }
diff --git a/kernel/sched/cpupri.h b/kernel/sched/cpupri.h
index f6d756173491..6b033347fdfd 100644
--- a/kernel/sched/cpupri.h
+++ b/kernel/sched/cpupri.h
@@ -17,7 +17,7 @@ struct cpupri_vec {
 
 struct cpupri {
         struct cpupri_vec pri_to_cpu[CPUPRI_NR_PRIORITIES];
-        int               cpu_to_pri[NR_CPUS];
+        int *cpu_to_pri;
 };
 
 #ifdef CONFIG_SMP
diff --git a/kernel/sched/cputime.c b/kernel/sched/cputime.c
index a95097cb4591..72fdf06ef865 100644
--- a/kernel/sched/cputime.c
+++ b/kernel/sched/cputime.c
@@ -332,50 +332,50 @@ out:
  * softirq as those do not count in task exec_runtime any more.
  */
 static void irqtime_account_process_tick(struct task_struct *p, int user_tick,
-                                                struct rq *rq)
+                                         struct rq *rq, int ticks)
 {
-        cputime_t one_jiffy_scaled = cputime_to_scaled(cputime_one_jiffy);
+        cputime_t scaled = cputime_to_scaled(cputime_one_jiffy);
+        u64 cputime = (__force u64) cputime_one_jiffy;
         u64 *cpustat = kcpustat_this_cpu->cpustat;
 
         if (steal_account_process_tick())
                 return;
 
+        cputime *= ticks;
+        scaled *= ticks;
+
         if (irqtime_account_hi_update()) {
-                cpustat[CPUTIME_IRQ] += (__force u64) cputime_one_jiffy;
+                cpustat[CPUTIME_IRQ] += cputime;
         } else if (irqtime_account_si_update()) {
-                cpustat[CPUTIME_SOFTIRQ] += (__force u64) cputime_one_jiffy;
+                cpustat[CPUTIME_SOFTIRQ] += cputime;
         } else if (this_cpu_ksoftirqd() == p) {
                 /*
                  * ksoftirqd time do not get accounted in cpu_softirq_time.
                  * So, we have to handle it separately here.
                  * Also, p->stime needs to be updated for ksoftirqd.
                  */
-                __account_system_time(p, cputime_one_jiffy, one_jiffy_scaled,
-                                        CPUTIME_SOFTIRQ);
+                __account_system_time(p, cputime, scaled, CPUTIME_SOFTIRQ);
         } else if (user_tick) {
-                account_user_time(p, cputime_one_jiffy, one_jiffy_scaled);
+                account_user_time(p, cputime, scaled);
         } else if (p == rq->idle) {
-                account_idle_time(cputime_one_jiffy);
+                account_idle_time(cputime);
         } else if (p->flags & PF_VCPU) { /* System time or guest time */
-                account_guest_time(p, cputime_one_jiffy, one_jiffy_scaled);
+                account_guest_time(p, cputime, scaled);
         } else {
-                __account_system_time(p, cputime_one_jiffy, one_jiffy_scaled,
-                                        CPUTIME_SYSTEM);
+                __account_system_time(p, cputime, scaled,       CPUTIME_SYSTEM);
         }
 }
 
 static void irqtime_account_idle_ticks(int ticks)
 {
-        int i;
         struct rq *rq = this_rq();
 
-        for (i = 0; i < ticks; i++)
-                irqtime_account_process_tick(current, 0, rq);
+        irqtime_account_process_tick(current, 0, rq, ticks);
 }
 #else /* CONFIG_IRQ_TIME_ACCOUNTING */
 static inline void irqtime_account_idle_ticks(int ticks) {}
 static inline void irqtime_account_process_tick(struct task_struct *p, int user_tick,
-                                                struct rq *rq) {}
+                                                struct rq *rq, int nr_ticks) {}
 #endif /* CONFIG_IRQ_TIME_ACCOUNTING */
 
 /*
@@ -464,7 +464,7 @@ void account_process_tick(struct task_struct *p, int user_tick)
                 return;
 
         if (sched_clock_irqtime) {
-                irqtime_account_process_tick(p, user_tick, rq);
+                irqtime_account_process_tick(p, user_tick, rq, 1);
                 return;
         }
 
diff --git a/kernel/sched/deadline.c b/kernel/sched/deadline.c
index b08095786cb8..800e99b99075 100644
--- a/kernel/sched/deadline.c
+++ b/kernel/sched/deadline.c
@@ -528,6 +528,7 @@ static enum hrtimer_restart dl_task_timer(struct hrtimer *timer)
         sched_clock_tick();
         update_rq_clock(rq);
         dl_se->dl_throttled = 0;
+        dl_se->dl_yielded = 0;
         if (p->on_rq) {
                 enqueue_task_dl(rq, p, ENQUEUE_REPLENISH);
                 if (task_has_dl_policy(rq->curr))
@@ -893,10 +894,10 @@ static void yield_task_dl(struct rq *rq)
          * We make the task go to sleep until its current deadline by
          * forcing its runtime to zero. This way, update_curr_dl() stops
          * it and the bandwidth timer will wake it up and will give it
-         * new scheduling parameters (thanks to dl_new=1).
+         * new scheduling parameters (thanks to dl_yielded=1).
          */
         if (p->dl.runtime > 0) {
-                rq->curr->dl.dl_new = 1;
+                rq->curr->dl.dl_yielded = 1;
                 p->dl.runtime = 0;
         }
         update_curr_dl(rq);
diff --git a/kernel/sched/fair.c b/kernel/sched/fair.c
index 7570dd969c28..0fdb96de81a5 100644
--- a/kernel/sched/fair.c
+++ b/kernel/sched/fair.c
@@ -6653,6 +6653,7 @@ static int idle_balance(struct rq *this_rq)
         int this_cpu = this_rq->cpu;
 
         idle_enter_fair(this_rq);
+
         /*
          * We must set idle_stamp _before_ calling idle_balance(), such that we
          * measure the duration of idle_balance() as idle time.
@@ -6705,14 +6706,16 @@ static int idle_balance(struct rq *this_rq)
 
         raw_spin_lock(&this_rq->lock);
 
+        if (curr_cost > this_rq->max_idle_balance_cost)
+                this_rq->max_idle_balance_cost = curr_cost;
+
         /*
-         * While browsing the domains, we released the rq lock.
-         * A task could have be enqueued in the meantime
+         * While browsing the domains, we released the rq lock, a task could
+         * have been enqueued in the meantime. Since we're not going idle,
+         * pretend we pulled a task.
          */
-        if (this_rq->cfs.h_nr_running && !pulled_task) {
+        if (this_rq->cfs.h_nr_running && !pulled_task)
                 pulled_task = 1;
-                goto out;
-        }
 
         if (pulled_task || time_after(jiffies, this_rq->next_balance)) {
                 /*
@@ -6722,9 +6725,6 @@ static int idle_balance(struct rq *this_rq)
                 this_rq->next_balance = next_balance;
         }
 
-        if (curr_cost > this_rq->max_idle_balance_cost)
-                this_rq->max_idle_balance_cost = curr_cost;
-
 out:
         /* Is there a task of a high priority class? */
         if (this_rq->nr_running != this_rq->cfs.h_nr_running &&